elie
@eliebakouch
training llm's @PrimeIntellect (prev: @huggingface)
anon feedback:
4.1K Following 15.1K Followers
we let opus 4.7 and gpt 5.5 run on the nanogpt optimizer speedrun: ~10k runs, 14k H200 hours, 23.9B tokens. opus hits 2930, codex 2950, both beating the human baseline of 2990. we cover claude autonomy failures, codex high compute usage, and much more
Show more
